8 papers
KANResDiff: Learning Local Residual Diffusion via Kolmogorov-Arnold Network for Ambiguous Medical Image Segmentation
Fanding Li, Chenglin Wang, Xiangyu Li +9
Ambiguous medical image segmentation aims to provide a series of diverse but plausible segmentation hypotheses. However, existing methods introduce stochasticity in a fixed and pre…
Phase singularity enabled polarization switchable analog spatial differentiation in an atomic MoS planar Fabry-Pérot cavity
Zhonglin Li, Yingying Wang, Jiawei Kang +3
Reconfigurable analog optical computing requires rapid and efficient switching between core mathematical operations, such as first- and second-order spatial differentiation. Here,…
Exact solution for a periodically driven magnetic multilayer system
P. I. Naumkin, A. V. Nikolaev, L. L. Tao +1
Periodic driving serves as an effective method for controlling the properties of physical systems. Called "Floquet engineering," it is a broad field of theoretical and experimental…
LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
Zhuo Chen, Xinzhe Yuan, Jianshu Zhang +8
The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). Howev…
Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
Xinzhe Yuan, Xiang Peng, Bin Gu +1
ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driven realizations for Transfor…
Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation
Fanding Li, Xiangyu Li, Xianghe Su +6
A simultaneous enhancement of accuracy and diversity of predictions remains a challenge in ambiguous medical image segmentation (AMIS) due to the inherent trade-offs. While truncat…